1
0

[HUDI-1331] Adding support for validating entire dataset and long running tests in test suite framework (#2168)

* trigger rebuild

* [HUDI-1156] Remove unused dependencies from HoodieDeltaStreamerWrapper Class (#1927)

* Adding support for validating records and long running tests in test sutie framework

* Adding partial validate node

* Fixing spark session initiation in Validate nodes

* Fixing validation

* Adding hive table validation to ValidateDatasetNode

* Rebasing with latest commits from master

* Addressing feedback

* Addressing comments

Co-authored-by: lamber-ken <lamberken@163.com>
Co-authored-by: linshan-ma <mabin194046@163.com>
This commit is contained in:
Sivabalan Narayanan
2020-12-26 12:29:24 -05:00
committed by GitHub
parent 3ec9270e8e
commit 8cf6a7223f
33 changed files with 1101 additions and 518 deletions

View File

@@ -1,3 +1,4 @@
hoodie.insert.shuffle.parallelism=100
hoodie.upsert.shuffle.parallelism=100
hoodie.bulkinsert.shuffle.parallelism=100
@@ -8,6 +9,13 @@ hoodie.deltastreamer.source.test.max_unique_records=100000000
hoodie.embed.timeline.server=false
hoodie.deltastreamer.source.input.selector=org.apache.hudi.integ.testsuite.helpers.DFSTestSuitePathSelector
hoodie.insert.shuffle.parallelism=100
hoodie.upsert.shuffle.parallelism=100
hoodie.bulkinsert.shuffle.parallelism=100
hoodie.deltastreamer.source.input.selector=org.apache.hudi.integ.testsuite.helpers.DFSTestSuitePathSelector
hoodie.datasource.hive_sync.skip_ro_suffix=true
hoodie.datasource.write.recordkey.field=_row_key
hoodie.datasource.write.keygenerator.class=org.apache.hudi.keygen.TimestampBasedKeyGenerator
hoodie.datasource.write.partitionpath.field=timestamp